Opportunity List Engine

1. A method for automatically identifying training opportunities for a plurality of advisors from a plurality of data sources across an enterprise, the method comprising: receiving, via a network interface of a computing device, historical sales data of each of a plurality of products and a selection of a client; identifying, by a regression analysis at the computing device, predictive factors based on the historical sales data; generating, at the computing device, a plurality of purchase likelihood models based on the predictive factors, each of the plurality of purchase likelihood models corresponding to one of the plurality of products; determining, at the computing device and based on the plurality of purchase likelihood models, likelihoods of the client purchasing each of a plurality of products; generating, at the computing device, a plurality of prioritized lists based on the likelihoods, wherein the prioritized lists includes sales opportunities lists; generating, at the computing device, an output interface to be transmitted to an advisor computer associated with a particular advisor, wherein the output interface is based on the plurality of prioritized lists; automatically determining, at the computing device and based on a portion of the historical sales data of the plurality of products associated with the particular advisor, a deficiency in training for the particular advisor for each one of the plurality of products; generating, at the computing device, scheduling data based on a sales production metric indicated by a portion of the historical sales data associated with a particular advisor and based on a sales opportunity indicated by at least one of the likelihoods that is associated with a particular product; and transmitting the output interface and the scheduling data from the computing device to the first local computing device via the network interface to cause display of a schedule of training opportunities associated with the particular product at the computing device.

2. The method of claim 1 , wherein the scheduling data is based on a gap between the sales production metric and the sales opportunity.

3. The method of claim 1 , further comprising validating the plurality of purchase likelihood models by applying each purchase likelihood models to a plurality of clients.

4. The method of claim 1 , further comprising scoring each purchase likelihood model and ranking a plurality of clients based on their purchase likelihood for each of the plurality of products.

5. The method of claim 1 , further comprising periodically validating the plurality of purchase likelihood models to assess model stability and robustness over time.

6. The method of claim 1 , wherein the plurality of products includes an investment product, a cash product, a liabilities product, an insurance product, a tax product, a retirement product, or any combination thereof.

7. The method of claim 1 , wherein the likelihoods of the client purchasing each of a plurality of products are determined based on predictive factors identified from a regression analysis, and wherein the predictive factors include an age, a geographic location, a net worth, an income, a debt, a family status, or any combination thereof.

8. The method of claim 1 , further comprising: receiving input indicating one or more opportunity suppression criteria; and removing one or more opportunities from a prioritized list based on the opportunity suppression criteria.

9. A non-transitory processor-readable medium storing instructions that, when executed by a processor, cause the processor to initiate or perform operations comprising: receiving, via a network interface of a computing device, historical sales data of each of a plurality of products and a selection of a client; identifying, by a regression analysis at the computing device, predictive factors based on the historical sales data; generating, at the computing device, a plurality of purchase likelihood models based on the predictive factors, each of the plurality of purchase likelihood models corresponding to one of the plurality of products; determining, at the computing device and based on the plurality of purchase likelihood models, likelihoods of the client purchasing each of a plurality of products; generating, at the computing device, a plurality of prioritized lists based on the likelihoods, wherein the prioritized lists includes sales opportunities lists; generating, at the computing device, an output interface to be transmitted to an advisor computer associated with a particular advisor, wherein the output interface is based on the plurality of prioritized lists; automatically determining, at the computing device and based on a portion of the historical sales data of the plurality of products associated with the particular advisor, a deficiency in training for the particular advisor for each one of the plurality of products; generating, at the computing device, scheduling data based on a sales production metric indicated by a portion of the historical sales data associated with a particular advisor and based on a sales opportunity indicated by at least one of the likelihoods that is associated with a particular product; and transmitting the output interface and the scheduling data from the computing device to the first local computing device via the network interface to cause display of a schedule of training opportunities associated with the particular product at the computing device.

10. The non-transitory processor-readable medium of claim 9 , wherein the scheduling data is based on a gap between the sales production metric and the sales opportunity.

11. The non-transitory processor-readable medium of claim 9 , further comprising validating the plurality of purchase likelihood models by applying each purchase likelihood models to a plurality of clients.

12. The non-transitory processor-readable medium of claim 9 , wherein the operations further comprise scoring each purchase likelihood model and ranking a plurality of clients based on their purchase likelihood for each of the plurality of products.

13. The non-transitory processor-readable medium of claim 9 , wherein the operations further comprise periodically validating the plurality of purchase likelihood models to assess model stability and robustness over time.

14. The non-transitory processor-readable medium of claim 9 , wherein the plurality of products includes an investment product, a cash product, a liabilities product, an insurance product, a tax product, a retirement product, or any combination thereof.

15. The non-transitory processor-readable medium of claim 9 , wherein the likelihoods of the client purchasing each of a plurality of products are determined based on predictive factors identified from a regression analysis, and wherein the predictive factors include an age, a geographic location, a net worth, an income, a debt, a family status, or any combination thereof.

16. The non-transitory processor-readable medium of claim 9 , wherein the operations further comprise: receiving input indicating one or more opportunity suppression criteria; and removing one or more opportunities from a prioritized list based on the opportunity suppression criteria.

17. A system comprising: a data input interface configured to receive historical sales data of each of a plurality of products and a selection of a client; a data storage device configured to store the historical sales data; and a processor operatively coupled to the data storage device, the processor configured to perform operations comprising: identifying, by a regression analysis, predictive factors based on the historical sales data; generating a plurality of purchase likelihood models based on the predictive factors, each of the plurality of purchase likelihood models corresponding to one of the plurality of products; determining, based on the plurality of purchase likelihood models, likelihoods of the client purchasing each of a plurality of products; generating a plurality of prioritized lists based on the likelihoods, wherein the prioritized lists includes sales opportunities lists; generating an output interface to be transmitted to an advisor computer associated with a particular advisor, wherein the output interface is based on the plurality of prioritized lists; automatically determining, based on a portion of the historical sales data of the plurality of products associated with the particular advisor, a deficiency in training for the particular advisor for each one of the plurality of products; generating scheduling data based on a sales production metric indicated by a portion of the historical sales data associated with a particular advisor and based on a sales opportunity indicated by at least one of the likelihoods that is associated with a particular product; and transmitting the output interface and the scheduling data from the computing device to the first local computing device via the network interface to cause display of a schedule of training opportunities associated with the particular product.